Ear recognition in a light field imaging framework: a new perspective

• Published in: IET biometrics Vol. 7; no. 3; pp. 224 - 231
• Main Authors: Sepas-Moghaddam, Alireza, Pereira, Fernando, Correia, Paulo Lobato
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 01.05.2018; John Wiley & Sons, Inc
• Subjects: 536 light field images; Angular momentum; Availability; Biometric recognition systems; biometric research; Biometrics; biometrics (access control); Cameras; Ear; ear images; ear piercing; ear recognition solution; earing; Electrons; feature extraction; Field cameras; forensic research; image recognition; image reconstruction; image sensors; image texture; imaging sensors; lenslet light field cameras; Light; Lytro ILLUM lenslet light field camera; nonlight field; novel Lenslet Light Field Ear DataBase; Performance evaluation; recent light field; Sensors; Special Issue: Unconstrained Ear Recognition; biometric research; ear recognition solution; recent light field; lenslet light field cameras; nonlight field; earing; image reconstruction; biometrics (access control); ear images; image texture; ear piercing; cameras; image sensors; imaging sensors; feature extraction; forensic research; novel Lenslet Light Field Ear DataBase; ear; 536 light field images; Lytro ILLUM lenslet light field camera; image recognition
• ISSN: 2047-4938; 2047-4946; 2047-4946
• DOI: 10.1049/iet-bmt.2017.0204

Ear recognition is an emerging research area in image-based biometrics. The commercial availability of lenslet light field cameras able to capture full spatio-angular information has brought momentum to biometric and forensic research exploiting this new type of imaging sensors. This study is the first to consider the usage of light field cameras for ear recognition, proposing both an appropriate content database and an ear recognition solution. The novel Lenslet Light Field Ear DataBase (LLFEDB) includes 536 light field images corresponding to four different poses, from 67 subjects, captured with a Lytro ILLUM lenslet light field camera. The LLFEDB includes critical cases such as ear images partly occluded by ear piercing, earing, hair and combination of occlusions. The novel light field-based ear recognition solution proposed exploits the richer spatio-angular information available in the light field images. A comparative performance evaluation study using the LLFEDB, and focusing on the most recent light field and non-light field based descriptors for ear recognition, shows a very promising performance of the proposed descriptor, outperforming all the assessed descriptors.